BOSS Zhipin Job Scraper

Scrapes BOSS直聘 (zhipin.com) job listings through Chrome CDP by keyword, city and filters, exporting plaintext-salary JSON/CSV plus summary reports.

Data & AnalyticsIntermediate★ 1,725⑂ 226AI score 8/10Last updated: Nov 3, 2026

What it does

Attaches to a logged-in Chrome via the DevTools Protocol and calls BOSS直聘's search API directly.
Returns plaintext salaries like 30-60K·15薪, bypassing the site's font-based anti-scraping on the frontend.
Collects listings plus detailed job descriptions and writes JSON / CSV (UTF-8 BOM, opens cleanly in Excel).
Generates an aggregate report with --analysis, and a job-market summary + resume-optimization prompt via job_summary.py.
Supports local company-name filtering (--company), merging and de-duplicating multiple runs (--merge), environment checks (--check) and smoke tests.
Uses a dedicated isolated Chrome profile at ~/.boss-zhipin-scraper/chrome-profile instead of your main browser.

Who it's for

Job seekers and researchers studying the Chinese job market (Shanghai, Beijing, Shenzhen, etc.).
Anyone who wants real data on salary bands, experience requirements and company size distribution.
People who prefer to pull structured data into Excel/Notion for their own analysis.

Example uses

--keyword "AI Agent" --city 上海 --pages 3 --format csv to export three pages of postings as CSV.
--detail --max-details 8 --analysis to fetch full JDs and produce a skills/salary breakdown report.
job_summary.py --company "字节跳动,SHEIN" --top 15 to summarize only selected companies and get resume-tuning prompts.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/eatmoreduck/boss-zhipin-scraper/HEAD/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the SKILL.m folder from the GitHub repo eatmoreduck/boss-zhipin-scraper into my ~/.claude/skills/boss-zhipin-scraper/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/eatmoreduck/boss-zhipin-scraper.git && mkdir -p ~/.claude/skills/boss-zhipin-scraper && cp -r boss-zhipin-scraper/SKILL.md boss-zhipin-scraper/scripts boss-zhipin-scraper/data ~/.claude/skills/boss-zhipin-scraper/

⚠ This is a third-party skill. Check the source repository before installing.

Make sure Chrome (or Edge) and Python 3.10+ are installed.
Clone the repository: git clone https://github.com/eatmoreduck/boss-zhipin-scraper.git
Create the skill folder and copy the files: mkdir -p ~/.claude/skills/boss-zhipin-scraper && cp -r boss-zhipin-scraper/SKILL.md boss-zhipin-scraper/scripts boss-zhipin-scraper/data ~/.claude/skills/boss-zhipin-scraper/
- If you use Hermes, copy the same files into ~/.hermes/skills/data-science/boss-zhipin-scraper/.
Install the Python dependencies: pip install websocket-client requests (or uv add websocket-client requests).
Run the environment check: python3 ~/.claude/skills/boss-zhipin-scraper/scripts/boss_cdp_raw.py --check --cdp-port 9222
If CDP is unreachable, run --setup-chrome --cdp-port 9222 and log in to zhipin.com in the dedicated Chrome window that opens.
In Claude Code, ask something like "search BOSS直聘 for AI engineer jobs in Shanghai" to trigger the skill.

View source on GitHub ↗License: MIT